The gap between abstract and concrete results in machine learning

DOI10.1080/09528139108915290zbMath0749.68075OpenAlexW2009656295MaRDI QIDQ4009244

Peter Turney

Publication date: 27 September 1992

Published in: Journal of Experimental & Theoretical Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/09528139108915290

zbMATH Keywords

biasPAC learningmachine learninglearning in the limitformal learning theory

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Ranking relations using analogies in biological and information networks

Cites Work

• Unnamed Item
• Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
• Occam's razor
• The Curve Fitting Problem: A Solution
• PROBLEMS WITH COMPLEXITY IN GOLD'S PARADIGM OF INDUCTION Part I: Dynamic Complexity
• PROBLEMS WITH COMPLEXITY IN GOLD'S PARADIGM OF INDUCTION Part II: Static Complexity
• Toward a mathematical theory of inductive inference
• Language identification in the limit

This page was built for publication: The gap between abstract and concrete results in machine learning